© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 1562
    Prev
    Next
    INDEX
    Explanations

    instances of the word "in" followed by another word

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "sitting in."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ŀ
    -0.68
     endors
    -0.64
    aler
    -0.64
    elf
    -0.62
    linger
    -0.59
    NOW
    -0.58
    llor
    -0.58
    lihood
    -0.58
    killed
    -0.54
     purch
    -0.54
    POSITIVE LOGITS
    ordinate
    1.15
     accordance
    1.02
    offensive
    1.01
    animate
    0.99
     situ
    0.99
     lieu
    0.98
     front
    0.97
     limbo
    0.95
    between
    0.95
    roads
    0.94
    Activations Density 0.225%

    No Known Activations